The discussion centers on the tension between leveraging AI for rapid development and maintaining architectural control, with users debating whether manual implementation of complex systems remains valuable for learning. A significant sub-thread highlights the severe financial impact large language models have on content creators, sparking debate over potential mitigation strategies.
1068 readable replies · Supporting reply 1 · Supporting reply 2 · Supporting reply 3 · Supporting reply 4vinhnx
VTCode
Rust2025–2026
vinhnx / VTCode
VTCode
VT Code is a terminal-first coding agent for your repo, in the CLI and native macOS app.
3Distinct people
56Mentions
1Explicit recommenders
909GitHub stars
What to know before exploring
What it is
VT Code is a terminal-first coding agent for your repo, in the CLI and native macOS app.
GitHub
Where it is used
No documented product use was verified in the last source check.
What people are saying
Thank you for checking out VT Code! “LLM-native code understanding” refers to VT Code's approach of using LLM as the primary mechanism for semantic code analysis rather than…
vinhnx used a recommendation phrase. 2 indexed comments match. This is a phrase match, not a verdict.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
- ratatui/awesome-ratatui · linked in 2 of the same discussions
Mentioned in the same Hacker News threads. That is not proof they are substitutes.
This week on Hacker News
Nov 8–Nov 15 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/15/2026, 2:59:53 AM UTC.
Developers are divided between migrating to third-party harnesses like Pi for their customizability and control, versus staying with native tools like Claude Code due to concerns about stability, security, and vendor restrictions. The strongest disagreement centers on whether the flexibility of open-source harnesses outweighs the operational risks of manual configuration and potential Terms of Service violations.
493 readable replies · Supporting reply 1 · Supporting reply 2 · Supporting reply 3 · Supporting reply 4Mentions over time
HN mentions by month56 dated mentions
Observed mentions: 2025-09-30 01:36:14 UTC to 2026-10-21 13:58:23 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Sep 2025 | 2025-09-01 00:00:00 UTC | 2025-10-01 00:00:00 UTC | 2 | 0 | 2 |
| Oct 2025 | 2025-10-01 00:00:00 UTC | 2025-11-01 00:00:00 UTC | 10 | 3 | 7 |
| Nov 2025 | 2025-11-01 00:00:00 UTC | 2025-12-01 00:00:00 UTC | 7 | 2 | 5 |
| Dec 2025 | 2025-12-01 00:00:00 UTC | 2026-01-01 00:00:00 UTC | 1 | 0 | 1 |
| Jan 2026 | 2026-01-01 00:00:00 UTC | 2026-02-01 00:00:00 UTC | 2 | 0 | 2 |
| Feb 2026 | 2026-02-01 00:00:00 UTC | 2026-03-01 00:00:00 UTC | 1 | 0 | 1 |
| Mar 2026 | 2026-03-01 00:00:00 UTC | 2026-04-01 00:00:00 UTC | 2 | 0 | 2 |
| Apr 2026 | 2026-04-01 00:00:00 UTC | 2026-05-01 00:00:00 UTC | 3 | 2 | 1 |
| May 2026 | 2026-05-01 00:00:00 UTC | 2026-06-01 00:00:00 UTC | 6 | 2 | 4 |
| Jun 2026 | 2026-06-01 00:00:00 UTC | 2026-07-01 00:00:00 UTC | 5 | 0 | 5 |
| Jul 2026 | 2026-07-01 00:00:00 UTC | 2026-08-01 00:00:00 UTC | 2 | 0 | 2 |
| Aug 2026 | 2026-08-01 00:00:00 UTC | 2026-09-01 00:00:00 UTC | 8 | 1 | 7 |
| Sep 2026 | 2026-09-01 00:00:00 UTC | 2026-10-01 00:00:00 UTC | 3 | 1 | 2 |
| Oct 2026 | 2026-10-01 00:00:00 UTC | 2026-11-01 00:00:00 UTC | 4 | 1 | 3 |
What Hacker News says
10 sourcesVIvinhnx·Oct 31, 2025
> Which model(s) are you running (e.g., Ollama, LM Studio, or others) and which open-source coding assistant/integration (for example, a VS Code plugin) you’re using?
Open-source coding assistant: VT Code (my own coding agent -- github.com/vinhnx/vtcode)
Model: gpt-oss-120b remote hosted via Ollama cloud experimental
> What laptop hardware do you have (CPU, GPU/NPU, memory, whether discrete GPU or integrated, OS) and how it performs for your workflow?
Macbook Pro M1
> What kinds of tasks you use it for (code completion, refactoring, debugging, code review) and how reliable it is (what works well / where it falls short).
All agentic coding workflow (debug, refactor, refine and testing sandbox execution). VT Code is currently in preview and being active developed, but currently it is mostly stable.
In Ask HN: Who uses open LLMs and coding assistants locally? Share setup and laptopI'm still refining and working on my coding agent, VT Code. Two weeks ago, I posted a comment [0] to regular Ask HN: What are you doing this week? and got out-of my expectation feedback. Thank you HN community!
The last 2 weeks I have been making constants and regular update to VT Code, and it still evolving to a hopefully more capable coding agent. Most recent notable release is official VS Code extension and OpenVSX distribution [1][2] so that you can use VT Code agent inside your favorite code IDE like VS Code, Windsurf, Cursor, Kiro and Eclipse.
About VT Code, it is a Rust-based terminal coding agent with semantic code intelligence via Tree-sitter (parsers for Rust, Python, JavaScript/TypeScript, Go, Java) and ast-grep (structural pattern matching and refactoring).
It supports multiple LLM providers: OpenAI, Anthropic, xAI, DeepSeek,
Read the rest
Gemini, OpenRouter, Z.AI, Moonshot AI, and MiniMax; all with automatic failover, prompt caching, and token-efficient context management. Configuration occurs entirely through vtcode.toml, sourcing constants from vtcode-core/src/config/constants.rs and model IDs from docs/models.json to ensure reproducibility and avoid hardcoding. [3]
Recently I've added Agent Client Protocol (ACP) integration. VT Code is now a fully compatible ACP agent, works with any ACP-clients: Zed (first-class support), Neovim, marimo notebook. [4]
[0] https://github.com/vinhnx/vtcode
[1] https://open-vsx.org/extension/nguyenxuanvinh/vtcode-compani...
[2] https://marketplace.visualstudio.com/items?itemName=nguyenxu...
[3] https://crates.io/crates/vtcode
[4] https://agentclientprotocol.com
Show HN: VT Code – LLM-agnostic coding agent with MCP/ACP and sandboxed tools
VT Code is a Rust CLI/TUI coding agent that works semantically on code (Tree-sitter + ast-grep), routes across multiple LLMs (incl. local via Ollama), and integrates with editors via ACP and external tools via MCP. It focuses on safety (workspace boundaries, per-tool Allow/Prompt/Deny, sandboxed commands/timeouts) and reproducibility (TOML config, caching, summarization).
What’s different:
- AST-aware search/refactors with preview-before-apply
- Provider-agnostic routing with failover and cost/latency-aware caching
- Policy-gated tools and strict workspace boundaries
- Terminal-first ergonomics you can script
Install:
cargo install vtcode
# or
brew install vinhnx/tap/vtcode
npm install -g vtcode
Quick start:
export OPENAI_API_KEY=... # or another provider key
vtcode
vtcode ask "Find md5 usages across the repo and propose
Read the rest
SHA-256 replacements (show diff)"
vtcode ask "Search for .unwrap() on Result and suggest safer handling"
Status: research preview (MIT). Feedback welcome on ergonomics, ACP/MCP DX, safety defaults, and real-world AST refactor recipes.
I submitted and reply to "Ask HN: What are you working on? (October 2025)" thread 7 days ago and receive out-of-expectation response. So, I will put my project here. Not totally vibe code, I prefer the term AI-assisted.
I'm currently building my own coding agent, VT Code. VT Code is a Rust-based terminal coding agent with semantic code intelligence via Tree-sitter (parsers for Rust, Python, JavaScript/TypeScript, Go, Java) and ast-grep (structural pattern matching and refactoring).
It supports multiple LLM providers: OpenAI, Anthropic, xAI, DeepSeek, Gemini, OpenRouter, Z.AI, Moonshot AI, all with automatic failover, prompt caching, and token-efficient context management. Configuration occurs entirely through vtcode.toml, sourcing constants from vtcode-core/src/config/constants.rs and model IDs from docs/models.json to ensure reproducibil
Read the rest
ity and avoid hardcoding. [0], [1], [2]
Recently I've added Agent Client Protocol (ACP) integration. VT Code is now a fully compatible ACP agent, works with any ACP-clients: Zed (first-class support), Neovim, marimo notebook. [3]
[0] https://github.com/vinhnx/vtcode
[1] https://crates.io/crates/vtcode
[2] https://docs.rs/vtcode
[3] https://agentclientprotocol.com/overview/agents
Thank you!
Show HN: VT Code – Research preview semantic coding agent
1 points · Open discussionShow HN: VT Code – AST-aware Rust agent for terminal (Tree-sitter/AST-grep)
VT Code is a Rust CLI/TUI coding agent for AST-aware edits (Tree-sitter, ast-grep). Multi-provider routing with failover and caching (OpenAI, Anthropic, Gemini, DeepSeek, xAI, OpenRouter, Z.AI, Moonshot; Ollama locally). Policy-gated tools, workspace boundaries, Zed ACP integration. Config-first via vtcode.toml; reproducible model/constant metadata in the repo.
Try it: cargo install vtcode; vtcode
Code: https://github.com/vinhnx/vtcode
6 points · Open discussionThank you, please let me know how could I can improve VT Code. Feel free to open an issue and I will check it https://github.com/vinhnx/vtcode
In Ask HN: What are you working on? (October 2025)Thank you for your very kind-words. I love building and agentic coding is my current curiosity.
> I’m curious though, how significant do you think it is for the agent to have semantic access through Tree-sitter?
For this, I'm really not sure, but since the start of building VT Code. I just had this idea to use tree-sitter to assist the agent to have more (or faster/more precise) semantic understanding of the coding, instead of relying them to figure out themself. For me, naively I think this could help agent to have better language-specific and accurately decision about the workspace (context) that they are working. If not having tree-sitter, I think the agent could eventually figure out itself. For this aspect, I should be research more on this topic. In VT Code, I included 6 language: Go, Python, Rust, TypeScript, Swift... ) via rust-b
Read the rest
inding crates, mostly when you launch the vtcode agent on any workspace, It will show the main languages in the workspace right way.
> Also what model have you had the most success with ?
I'm having mainly limited-budget so I can only use OpenRouter and utilize its vast amount models support. So that I can prototype quickly, for different use-cases. For VT Code agent, I'm using mainly x-ai/grok-code-fast-1, in my experience, it most suit for building VT Code agent it self because of speeds, and versatile in function calling and have good instruction following. I also have good successes with x-ai/grok-4-fast. I have not tried claude-4.5-sonnet and gpt-5/gpt-5-codex though. I really love to run benchmarks for VT Code to see how it perform in real world coding task, I'm aiming for Aider polygot bench, terminal-bench and swe-bench-lite, it is in my plan for now in my GitHub issues.
For VT Code itself, I instruct it to strictly follow system-prompt, in which I take various inspiration from Anthropic, OpenAI and Devin guide/blogs on how to build coding agent. But, for a model-agnostic agent, the capability to support multi providers and multi models is a challenge. For this I think I need help. I'm fortunately to have support from open-source community suggesting me to use zig, I have had good success with it so far, for implement LLM calls and implement the /model picker.
Overall in my experience building VT, the most important aspect of effective coding agent is context engineering, like all big-lab has research. A good system prompt is also very important, but not context is everything. https://github.com/vinhnx/vtcode/blob/main/prompts/system.md
// Sorry, English is not my main language, so pardon the typo and grammar. Thank you!
I'm currently building my own coding agent, VT Code. VT Code is a Rust-based terminal coding agent with semantic code intelligence via Tree-sitter (parsers for Rust, Python, JavaScript/TypeScript, Go, Java) and ast-grep (structural pattern matching and refactoring).
It supports multiple LLM providers: OpenAI, Anthropic, xAI, DeepSeek, Gemini, OpenRouter, Z.AI, Moonshot AI, all with automatic failover, prompt caching, and token-efficient context management. Configuration occurs entirely through vtcode.toml, sourcing constants from vtcode-core/src/config/constants.rs and model IDs from docs/models.json to ensure reproducibility and avoid hardcoding. [0], [1], [2]
Recently I've added Agent Client Protocol (ACP) integration. VT Code is now a fully compatible ACP agent, works with any ACP-clients: Zed (first-class support), Neovim, marimo note
Read the rest
book. [3]
[0] https://github.com/vinhnx/vtcode
[1] https://crates.io/crates/vtcode
[2] https://docs.rs/vtcode
[3] https://agentclientprotocol.com/overview/agents
Thank you!
I'm currently building my own coding agent, mainly for self-research [0], so this article is very helpful to me. Thank you Simon!
In this particular thread, other has commented about lightweight sandboxing solution. I think I will integrate this next in my agent for safe code execution. [1]
[0] https://github.com/vinhnx/vtcode
[1] https://news.ycombinator.com/item?id=45429787
In Designing agentic loops